We present a closed-loop framework for autonomous raceline optimization that combines NURBS-based trajectory representation, CMA-ES global trajectory optimization, and controller-guided spatial feedback. Instead of treating tracking errors as transient disturbances, our method exploits them as informative signals of local track characteristics via a Kalman-inspired spatial update. This enables the construction of an adaptive, acceleration-based constraint map that iteratively refines trajectories toward near-optimal performance under spatially varying track and vehicle behavior. In simulation, our approach achieves a 17.38% lap time reduction compared to a controller parametrized with maximum static acceleration. On real hardware, tested with different tire compounds ranging from high to low friction, we obtain a 7.60% lap time improvement without explicitly parametrizing friction. This demonstrates robustness to changing grip conditions in real-world scenarios.
Fig. 3: Track segmentation into acceleration (red) and deceleration (blue) zones for blame region identification. Since the trajectory does not contain any neutral phases, these are not represented in the figure.
Fig. 4: F1Tenth experimental platform with Asus NUC and Hokuyo LiDAR.
Map
Ours
Ours
Min Curvature
Homeomorphism
Static
Adaptive
Static
Static
F1Aut
20.02
16.54
22.12
21.83
Wall1
16.82
15.71
17.32
16.92
Levine
11.08
10.42
11.39
12.18
Operngasse
7.49
6.24
8.37
7.58
TABLE I: Lap times in s for different trajectories and racetracks.
Fig. 5: Optimizer convergence on F1Aut track. Red line: Error feedback activation. Convergence is achieved within 8 laps, with 500 iterations/lap.
Fig. 6: llustration of the two artificially introduced low-friction regions (highlighted in gray) and the corresponding evolution of the optimized trajectory across three laps, showing the nominal planned trajectory (red-dotted line), the executed trajectory (blue line), and updated constraint map (shaded blue and red regions).
Fig. 7: Lap times for three tire configurations (Low/Medium/High friction). Error feedback activated at lap 0.
Fig. 8: Optimized trajectories under different global friction conditions showing the lateral acceleration a⊥ , the longitudinal acceleration a∥ , and the acceleration constraints amax from the constraint map. Higher-friction setups produce trajectories with increased average velocity and slightly longer path lengths, while lower-friction setups result in reduced speeds and more circular trajectories.
Professorship of Autonomous Vehicle Systems, TUM School of Engineering and Design, Technical University of Munich, 85748 Garching, Germany; Munich Institute of Robotics and Machine Intelligence (MIRMI)